A QGI result should be inspectable, reproducible and challengeable.
R4 defines the evidence packet that must sit behind a public demonstration result: exact task and system manifests, runtime, lineage, raw outputs, metrics, uncertainty, resources, provenance, signatures, attestations and challenges.
The result is the end of an evidence chain, not the beginning of a claim.
packet_idprotocol_versiondemonstration_idevaluation_idtask_manifest_hashsystem_manifest_hashenvironment_hashdataset_lineage_hashmodel_solver_simulator_manifestraw_output_hashesmetric_recordsuncertainty_recordsresource_recordsfailure_recordsprovenance_recordsattestation_refschallenge_refssignaturespublished_atFailures and contradictions remain part of the scientific record.
No result may be described as a QGI capability claim unless the corresponding task and evaluation manifests were registered before result publication.
Result pages must expose domain-native metrics, uncertainty, resource use, baselines, failures and evidence references together.
A demonstration may publish evidence without receiving any QGI level.
Challenges and contradictory evidence remain visible and must not be silently deleted from the publication history.
Public QGI R5 ships with no fabricated demonstration results, calibrated thresholds or certifications. Real result records may appear only after controlled operator publication of evidence bundles.
Evidence can evolve without rewriting history.
A public demonstration may move from planning through evidence publication and later become challenged or withdrawn. The state changes; the signed history remains visible.
R4 publishes a protocol, not invented evidence.
The machine-readable evidence schema ships with example_packets, published_results and certifications empty.